Rotation Invariant Spatial Pyramid Matching for Image Classification

Karmakar, Purnendu; Teng, Shyh Wei; Lu, Guojun; Zhang, Dengsheng

doi:10.1109/dicta.2015.7371303

Cited by 8 publications

(13 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To prove the effectiveness of the proposed approach, in addition to looking at methods concurrent to our approach [18,37,15], we have also selected some recent state-of-theart papers which are focussed on different approaches such as feature extraction [39,8,9] and intermediate feature representation [21,22,7] techniques to improve classification performance. Mekhalfi et al [21] propose a novel scheme to compactly represent images, using a compressive sensing and multi-feature framework.…”

Section: Related Workmentioning

confidence: 99%

“…SPM is considered an extension of the order-less BoVW and it addresses the shortcoming of a lack of spatial information [5,37,6]. However, if the objects in the images are flipped or rotated, the discrimination power of SPM decreases [37,15]. Zhao et al [37] propose a Concentric Circle-structured Multiscale BoVW model (CCM-BOVW) to incorporate rotation-invariant spatial layout information of images into the BoVW model for land-use scene classification.…”

Section: Introductionmentioning

confidence: 99%

“…According to Karmakar et al [15], the construction of histograms over the concentric rectangles makes it possible to deal with image rotations and changes in view point. In this paper, we aim to address this problem by proposing a novel images representation that is based on histograms of concentric weighted circles.…”

Section: Introductionmentioning

confidence: 99%

“…The upper region of Fig. 1 represents the idea of histograms constructed over the concentric rectangular regions [15], while the lower region represents the histograms con- Fig. 1.…”

Section: Introductionmentioning

confidence: 99%

“…The visual words using rectangle coordinates are not equidistant from the center, so rotation invariance is not achieved, while in the circle, all points are equidistant from the center so it achieves rotation invariance (as compared to [15]).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Intelligent image classification-based on spatial weighted histograms of concentric circles

Zafar

Ashraf

Ali

et al. 2018

ComSIS

View full text Add to dashboard Cite

As digital images play a vital role in multimedia content, the automatic classification of images is an open research problem. The Bag of Visual Words (BoVW) model is used for image classification, retrieval and object recognition problems. In the BoVW model, a histogram of visual words is computed without considering the spatial layout of the 2-D image space. The performance of BoVW suffers due to a lack of information about spatial details of an image. Spatial Pyramid Matching (SPM) is a popular technique that computes the spatial layout of the 2-D image space. However, SPM is not rotation-invariant and does not allow a change in pose and view point, and it represents the image in a very high dimensional space. In this paper, the spatial contents of an image are added and the rotations are dealt with efficiently, as compared to approaches that incorporate spatial contents. The spatial information is added by constructing the histogram of circles, while rotations are dealt with by using concentric circles. A weighed scheme is applied to represent the image in the form of a histogram of visual words. Extensive evaluation of benchmark datasets and the comparison with recent classification models demonstrate the effectiveness of the proposed approach. The proposed representation outperforms the state-of-the-art methods in terms of classification accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…The upper region of Fig. 1 represents the idea of histograms constructed over the concentric rectangular regions [15], while the lower region represents the histograms con- Fig. 1.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Intelligent image classification-based on spatial weighted histograms of concentric circles

Zafar

Ashraf

Ali

et al. 2018

ComSIS

View full text Add to dashboard Cite

show abstract

An Enhancement to the Spatial Pyramid Matching for Image Classification and Retrieval

Karmakar

Teng

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Spatial pyramid matching (SPM) is one of the widely used methods to incorporate spatial information into the image representation. Despite its effectiveness, the traditional SPM is not rotation invariant. A rotation invariant SPM has been proposed in the literature but it has many limitations regarding the effectiveness. In this paper, we investigate how to make SPM robust to rotation by addressing those limitations. In an SPM framework, an image is divided into an increasing number of partitions at different pyramid levels. In this paper, our main focus is on how to partition images in such a way that the resulting structure can deal with image-level rotations. To do that, we investigate three concentric ring partitioning schemes. Apart from image partitioning, another important component of the SPM framework is a weight function. To apportion the contribution of each pyramid level to the final matching between two images, the weight function is needed. In this paper, we propose a new weight function which is suitable for the rotation-invariant SPM structure. Experiments based on image classification and retrieval are performed on five image databases. The detailed result analysis shows that we are successful in enhancing the effectiveness of SPM for image classification and retrieval. INDEX TERMS Spatial pyramid matching, rotation invariance, image classification, image retrieval.

show abstract